Search Results

The Tempus Pro is a portable vital signs monitor intended to be used by clinicians and medically qualified personnel for the attended or unattended monitoring of single or multiple vital signs in clinical and pre-hospital care applications. The device is indicated for 3 & 5 Lead ECG monitoring and 12 Lead ECG recording with interpretation, impedance pneumography, non-invasive blood pressure (NIBP), endtidal CO2 (ETCO2), respiration rate, pulse oximetry (SpO2), contact temperature, invasive pressure and extended pulse oximetry capability including; carboxy haemoglobin (SpCO), metheglobin (SpMet), total haemoglobin (SpHb) and total oxygen content (SpOC) measurements.

The monitor is intended to be used as a stand-alone monitor or as a telemedicine system (transmitting patient data to other medical professionals located elsewhere).

The device is indicated for adults, pediatrics and neonates.

The Tempus Pro is a multi-parameter vital signs monitor designed for use in pre-hospital care and remote clinical locations by trained healthcare professionals. It provides 3&5 lead ECG monitoring, 12 lead ECG recording, pulse oximetry, non-invasive blood pressure, sidestream capnometry, contact temperature, impedance respiration, invasive pressure and user configurable alarms.

In addition, it provides the ability to transmit all vital signs data via wired or wireless connections to a software system (called i2i) expected to be based in a facility far from the user e.g. a response centre facility. In addition to sending all vital signs, the system can also send pictures or video via an integrated camera, geographic position by an integrated GP$ receiver and voice via a wired or wireless headset.

Here's an analysis of the Tempus Pro (EF) medical device submission based on the provided document, focusing on acceptance criteria and supporting studies.

1. Table of Acceptance Criteria and Reported Device Performance

The provided document describes non-clinical testing to ensure the device meets safety and performance standards. It does not contain specific quantitative "acceptance criteria" and "reported performance" like sensitivity/specificity for a diagnostic AI model. Instead, the acceptance criteria are implicit: successful completion of tests according to relevant international standards and equivalence to predicate devices.

2. Sample Size Used for the Test Set and Data Provenance

The document describes non-clinical engineering and bench testing, not a clinical study with a "test set" in the sense of a dataset for an AI algorithm. Therefore, no specific sample sizes for a test set are mentioned, nor is there data provenance in terms of country of origin or retrospective/prospective for a clinical dataset. The testing primarily involved the device itself and its components.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications

Since this is a submission for a vital signs monitor and not an AI-driven diagnostic device requiring expert interpretation of outputs, there were no experts used to establish ground truth for a test set in the typical sense. Expertise was likely involved in setting the testing standards and interpreting the results of the engineering tests (e.g., verifying compliance with IEC standards), but this is not specified as "ground truth establishment."

4. Adjudication Method for the Test Set

As there is no diagnostic "test set" with subjective interpretations, no adjudication method (like 2+1 or 3+1) was used or mentioned.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size

No MRMC comparative effectiveness study was done or reported. The device is a vital signs monitor, and the submission focuses on verifying its technical performance and substantial equivalence to predicate devices, not on the improvement of human reader performance with AI assistance. The "AI" component mentioned is the "interpretation output" of the mymisys32.dll for 12-Lead ECG, but this is presented as a pre-existing component from a cleared device (QRS Diagnostic CardioView K083749) that is now being displayed, rather than a new AI requiring an MRMC study for effectiveness.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

The 12-Lead ECG interpretation (part of the mymisys32.dll) is an algorithmic function. The submission indicates that "the interpretation output of the ■ mymisys32.dll, which is already an integral part of the cleared Tempus Pro, but the interpretation output is not currently displayed to the user." It further states that this dll is part of a previously cleared software package (QRS Diagnostic CardioView K083749).

This means the algorithm for ECG interpretation has been evaluated in standalone fashion as part of its original clearance (K083749). For this specific submission, the focus is on the safety and effectiveness of displaying this pre-existing interpretation, rather than re-evaluating the algorithm itself. Yes, a standalone evaluation of this ECG interpretation algorithm would have been done for its original clearance, and the current submission relies on that prior clearance.

7. The Type of Ground Truth Used

For the engineering and bench testing, the "ground truth" was established by objective technical specifications and compliance with international standards (e.g., IEC60601-1, IEC 9919, RTCA DO-160). For the ECG interpretation component (mymisys32.dll), its original clearance (K083749) would have relied on expert consensus or clinically validated ECG databases to establish ground truth for its interpretive accuracy, though this is not detailed in the provided document.

8. The Sample Size for the Training Set

This document does not describe the development or training of a de novo AI algorithm. The components added (Masimo SET Rainbow module, Medlab IBP module, QRS Diagnostic CardioView dll) are all from established, previously cleared predicate devices. Therefore, no sample size for a training set for the Tempus Pro (EF) itself is mentioned. Any training data for the individual components (like the ECG interpretation algorithm) would have been part of their original development and clearance, which is not detailed here.

9. How the Ground Truth for the Training Set Was Established

Given that no de novo AI algorithm training is described for the Tempus Pro (EF) in this submission, the establishment of ground truth for a training set is not applicable to this document. For the pre-existing components (e.g., the ECG interpretation algorithm), ground truth for their training would have been established during their original development, likely through expert cardiologist consensus on annotated ECG waveforms or through comparison with established diagnostic methods.

Ask a specific question about this device